Abstract
We present a monolingual alignment system
for long, sentence- or clause-level alignments,
and demonstrate that systems designed for
word- or short phrase-based alignment are illsuited for these longer alignments. Our system is capable of aligning semantically similar spans of arbitrary length. We achieve significantly higher recall on aligning phrases of
four or more words and outperform state-ofthe-art aligners on the long alignments in the
MSR RTE corpus